Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 37 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2531. Min Range: -2.2531

Max Act: 2.2531. Min Act: -0.0000

Data Index: 278663 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.9615. Min Act: -0.0000

Data Index: 721921 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 2.2531. Min Range: -2.2531

Max Act: 2.0791. Min Act: -0.0000

Data Index: 574768 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.5506. Min Act: -0.0000

Data Index: 1345914 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.4558. Min Act: -0.0000

Data Index: 684908 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.3416. Min Act: -0.0000

Data Index: 817316 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.5034. Min Act: -0.0000

Data Index: 736292 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.4494. Min Act: -0.0000

Data Index: 788188 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.3122. Min Act: -0.0000

Data Index: 923191 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.3676. Min Act: -0.0000

Data Index: 23938 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.3609. Min Act: -0.0000

Data Index: 1227493 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.2696. Min Act: -0.0000

Data Index: 71221 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.4313. Min Act: -0.0000

Data Index: 556389 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.4308. Min Act: -0.0000

Data Index: 242793 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.4681. Min Act: -0.0000

Data Index: 1193700 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.1618. Min Act: -0.0000

Data Index: 95832 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.3026. Min Act: -0.0000

Data Index: 321092 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.2999. Min Act: -0.0000

Data Index: 618553 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.2881. Min Act: -0.0000

Data Index: 1318205 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 2.2531. Min Range: -2.2531

Max Act: 1.2803. Min Act: -0.0000

Data Index: 348826 (C4 (Web Text))

Max Activating Token Index: 972